Back to Browse

Agentdrive MCP Server

Developer ToolsModerate5.2MCP RegistryLocalRemote
Free

Server data from the Official MCP Registry

Cross-agent artifact workspace with provenance across Claude Code, Codex, Cursor, LangGraph.

About

Cross-agent artifact workspace with provenance across Claude Code, Codex, Cursor, LangGraph.

Remote endpoints: streamable-http: https://mcp.agentdrive.sh/mcp

Security Report

5.2
Moderate5.2Moderate Risk

AgentDrive MCP server is well-structured with proper authentication via API keys and appropriate permissions scoped to its purpose. Code quality is solid with input validation via Zod schemas, proper error handling, and no malicious patterns detected. Minor code quality issues around broad exception handling and some logging practices are present but do not indicate security vulnerabilities. Supply chain analysis found 5 known vulnerabilities in dependencies (2 critical, 3 high severity).

7 files analyzed · 10 issues found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

HTTP Network Access

Connects to external APIs or services over the internet.

env_vars

Check that this permission is expected for this type of plugin.

How to Install & Connect

Available as Local & Remote

This plugin can run on your machine or connect to a hosted endpoint. during install.

Documentation

View on GitHub

From the project's GitHub README.

AgentDrive MCP Server

The official Model Context Protocol server for AgentDrive — a cross-agent artifact workspace with provenance and portable storage across Claude Code, Codex, Cursor, LangGraph, and any MCP-aware host.

Give your agents a shared, persistent workspace: files with versioning, semantic recall over everything prior agents produced, run logging, and cross-agent attribution — so the next session (on any tool) picks up where the last one left off.

Get an API key (free)

Create one at https://app.agentdrive.sh — no credit card. The free tier (1 workspace, 1 GB storage, 10k embeddings) is free indefinitely.

Two ways to connect

1. Hosted (no install) — Streamable HTTP

Point any MCP client that supports remote servers at the hosted endpoint and pass your key as a bearer token:

URL:    https://mcp.agentdrive.sh/mcp
Header: Authorization: Bearer agentdrive_live_xxx

Or install in one click via Smithery.

2. Local (stdio) — via npx

{
  "mcpServers": {
    "agentdrive": {
      "command": "npx",
      "args": ["-y", "@adrive/mcp-server"],
      "env": {
        "AGENTDRIVE_API_KEY": "agentdrive_live_xxx"
      }
    }
  }
}

Add that block to your host's MCP config:

  • Claude Desktop: claude_desktop_config.json
  • Cursor: ~/.cursor/mcp.json
  • Claude Code: claude mcp add agentdrive -- npx -y @adrive/mcp-server (set AGENTDRIVE_API_KEY in env)
  • Codex / Cline / Continue / Zed: the standard mcpServers block above

The fastest path is the AgentDrive installer, which auto-wires every detected host:

curl -fsSL agentdrive.sh/install | sh

Configuration

Env varRequiredDefaultDescription
AGENTDRIVE_API_KEYyesYour AgentDrive API key (agentdrive_live_...).
AGENTDRIVE_API_URLnohttps://app.agentdrive.shOverride the API endpoint (self-hosted worker).
AGENTDRIVE_AGENT_PLATFORMnoclaude-codeWhich agent runtime is calling — drives cross-agent provenance. One of claude-code, codex, cursor, langgraph, crewai, autogen, cline, continue, zed, unknown.
AGENTDRIVE_AGENT_ROLEnoFree-text role label (e.g. planner, reviewer) to distinguish multiple agents on the same platform.

Tools

20 tools across files, memory, collaboration, org, and provenance.

ToolCategoryDescription
drive_contextmemoryAuto-pull the most relevant prior artifacts for the task you're starting.
drive_searchmemorySemantic search across your org's artifacts.
drive_recallmemoryRecall persistent facts/preferences agents have written.
drive_writefilesWrite a markdown file (auto-versioned).
drive_readfilesRead a file's content.
drive_listfilesList files in a workspace.
drive_deletefilesDelete a file.
drive_versionsfilesView a file's version history.
drive_sharecollaborationGenerate a (optionally email-gated) share link.
drive_commentcollaborationComment on a file.
drive_feedbackcollaborationRead human comments on a file.
drive_activityprovenanceRecent workspace activity (writes, comments, shares).
drive_log_runprovenanceLog an agent run (task, status, artifacts, identity).
drive_inviteorgInvite a human to your org by email.
drive_rolesorgAssign/list/remove per-workspace access by email.
drive_orgorgView org details: agents, members, plan, usage.
drive_sandbox_clonesandbox (experimental)Clone a git repo into a per-workspace Linux sandbox.
drive_sandbox_execsandbox (experimental)Run a shell command in the sandbox.
drive_sandbox_readsandbox (experimental)Read a file from the sandbox filesystem.
drive_sandbox_commitsandbox (experimental)Stage + commit the sandbox worktree.

The drive_sandbox_* tools require the Cloudflare Containers plan on the AgentDrive worker and degrade cleanly to a "not configured" message otherwise.

Why AgentDrive

Agents lose context at every session boundary and every tool switch. AgentDrive is the shared substrate: one workspace, every agent, full provenance. Write once with Claude Code; recall it from Cursor; hand off to Codex — each call is attributed to the right principal and platform.

Develop

npm install
npm run build      # tsc -> dist/
npm test           # vitest

License

Apache-2.0. See LICENSE.

Reviews

No reviews yet

Be the first to review this server!